Surface Shape Description of 3D Data from Under Vehicle Inspection Robot Sreenivas R. Sukumar 1 , David L. Page 1 , Andrei V. Gribok 1 , Andreas F. Koschan 1 , Mongi A. Abidi 1 , David J. Gorsich 2 and Grant R. Gerhart 2 1 Imaging, Robotics, and Intelligent Systems Laboratory, The University of Tennessee Knoxville, TN, USA 37996-2100; 2 U. S. Army RDECOM Tank-Automotive Research, Development and Engineering Center, Waren, MI, USA 48397-5000 ABSTRACT Our research efforts focus on the deployment of 3D sensing capabilities to a multi-modal under vehicle inspection robot. In this paper, we outline the various design challenges towards the automation of the 3D scene modeling task. We employ laser-based range imaging techniques to extract the geometry of a vehicle’s undercarriage and present our results after range integration. We perform shape analysis on the digitized triangle mesh models by segmenting them into smooth surface patches based on the curvedness of the surface. Using a region-growing procedure, we then obtain the patch adjacency. On each of these patches, we apply our definition of the curvature variation measure (CVM) as a descriptor of surface shape complexity. We base the information-theoretic CVM on shape curvature, and extract shape information as the entropic measure of curvature to represent a component as a graph network of patches. The CVM at the nodes of the graph describe the surface patch. We then demonstrate our algorithm with results on automotive components. With apriori manufacturer information about the CAD models in the undercarriage we approach the technical challenge of threat detection with our surface shape description algorithm on the laser scanned geometry. Keywords: under vehicle inspection, laser range scanning, automotive component description, surface description, 3D surface feature. 1. INTRODUCTION Under vehicle inspection has been traditionally accomplished through inspection personnel walking around the vehicle with a mirror at the end of a stick. The inspection personnel identify weapons, bombs and other security threats based on what they see on the mirror. The mirror-on-the-stick system allows only partial coverage under a vehicle and is restricted by ambient lighting during the day and requires a flash light in the night when there is very limited lighting. Such a system also places the inspecting personnel at an endangering risk of a possible detonation. As part of the Security Automation and Future Electromotive Robotics (SAFER) program [1] we are developing a robotic platform that deploys “sixth sense” sensors for threat assessment. In this paper, we present results on the idea of incorporating a 3D range sensor on a robot to identify suspicious objects. Our 3D sensing modality provides the flexibility of deployment without considering the ambient lighting. In addition, our system enhances the ease of visualization and the possibility of automating threat assessment. In Figure 1, we show the robotic platform and the 3D geometry of the scene containing the muffler, shaft and the catalytic converter. With prior manufacturer’s information on the components that make the undercarriage of the vehicle, threat Further author information: Email: ssrangan@utk.edu ; phone: (865) 974-9213; fax: (865) 974-5459 Unmanned Ground Vehicle Technology VII, edited by Grant R. Gerhart, Charles M. Shoemaker, Douglas W. Gage, Proceedings of SPIE Vol. 5804 (SPIE, Bellingham, WA, 2005) · 0277-786X/05/$15 · doi: 10.1117/12.602930 621 S. Sukumar, D. Page, A. Gribok, A. Koschan, M. Abidi, D. Gorsich, and G. Gerhart, "Surface Shape Description of 3D Data from Under Vehicle Inspection Robot," Proc. SPIE Unmanned Ground Vehicle Technology VII, Vol. 5804, Orlando, FL, pp. 621-629, March 2005. 195